Optimizing Classification Accuracy of Remotely Sensed Imagery with DT-CWT Fused Images

Image fusion is a basic tool for combining low spatial resolution multi-spectral and high spatial resolution panchromatic images using advanced image processing techniques. Study on efficient image fusion method for specific application is one of the most important objectives in current remote sensing community. On the other hand, it is well known that the image classification techniques combine complex processes that may be affected by factors like the resolution of remote sensed images. This study focuses on the influence of image fusion on spectral classification algorithms and their accuracy. Results are presented on SPOT images. The best results were achieved by Dual Tree Complex Wavelet Transform (DT-CWT)).